{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/uncertainty-aware-meta-learning-for","title":"Uncertainty-Aware Meta-Learning for Multimodal Task Distributions","arxiv_id":"2210.01881","date":"2022-10-04","proceeding":null,"authors":["Cesar Almecija","Apoorva Sharma","Navid Azizan"],"abstract":"Meta-learning or learning to learn is a popular approach for learning new tasks with limited data (i.e., few-shot learning) by leveraging the commonalities among different tasks. However, meta-learned models can perform poorly when context data is limited, or when data is drawn from an out-of-distribution (OoD) task. Especially in safety-critical settings, this necessitates an uncertainty-aware approach to meta-learning. In addition, the often multimodal nature of task distributions can pose unique challenges to meta-learning methods. In this work, we present UnLiMiTD (uncertainty-aware meta-learning for multimodal task distributions), a novel method for meta-learning that (1) makes probabilistic predictions on in-distribution tasks efficiently, (2) is capable of detecting OoD context data at test time, and (3) performs on heterogeneous, multimodal task distributions. To achieve this goal, we take a probabilistic perspective and train a parametric, tuneable distribution over tasks on the meta-dataset. We construct this distribution by performing Bayesian inference on a linearized neural network, leveraging Gaussian process theory. We demonstrate that UnLiMiTD's predictions compare favorably to, and outperform in most cases, the standard baselines, especially in the low-data regime. Furthermore, we show that UnLiMiTD is effective in detecting data from OoD tasks. Finally, we confirm that both of these findings continue to hold in the multimodal task-distribution setting.","url_abs":"https://arxiv.org/abs/2210.01881v1","url_pdf":"https://arxiv.org/pdf/2210.01881v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"uncertainty-aware-meta-learning-for","repo_url":"https://github.com/azizanlab/unlimitd","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.01881","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}